AI agents call get_invoice_pdf to retrieve information from Sevdesk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves an existing invoice PDF in base64 format from the sevdesk accounting system. It performs a query/fetch operation that reads data without modifying, deleting, or executing any external operations. No financial transactions, state changes, or destructive actions occur. This is a straightforward Read operation with minimal blast radius.
From the tool's definition Tool name is 'get_invoice_pdf' and description states 'Get invoice PDF as base64 from sevdesk'. The verb 'get' and action of retrieving a PDF document indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Get invoice PDF as base64 from sevdesk. It is categorised as a Read tool in the Sevdesk MCP Server, which means it retrieves data without modifying state.
Register the Sevdesk MCP server in PolicyLayer and add a rule for get_invoice_pdf: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sevdesk. Nothing to install.
get_invoice_pdf is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_invoice_pdf rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_invoice_pdf. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_invoice_pdf is provided by the Sevdesk MCP server (codestra/sevdesk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →